Arabic T5ForConditionalGeneration Base Cased model (from UBC-NLP)

Description

Pretrained T5ForConditionalGeneration model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. AraT5-base-title-generation is a Arabic model originally trained by UBC-NLP.

Live Demo Open in Colab Download Copy S3 URI

How to use

documentAssembler = DocumentAssembler() \
    .setInputCol("text") \
    .setOutputCol("document")

t5 = T5Transformer.pretrained("t5_arat5_base_title_generation","ar") \
    .setInputCols(["document"]) \
    .setOutputCol("answers")

pipeline = Pipeline(stages=[documentAssembler, t5])

data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text")

result = pipeline.fit(data).transform(data)

val documentAssembler = new DocumentAssembler()
      .setInputCols("text")
      .setOutputCols("document")

val t5 = T5Transformer.pretrained("t5_arat5_base_title_generation","ar")
    .setInputCols("document")
    .setOutputCol("answers")

val pipeline = new Pipeline().setStages(Array(documentAssembler, t5))

val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text")

val result = pipeline.fit(data).transform(data)

Model Information

References

• https://huggingface.co/UBC-NLP/AraT5-base-title-generation
• https://aclanthology.org/2022.acl-long.47/
• https://doi.org/10.14288/SOCKEYE
• https://www.tensorflow.org/tfrc